# OpenAI — Continuously hardening ChatGPT Atlas against prompt injection

- Company: OpenAI (openai.com)
- Announced: 2025-12-22T00:00:00+00:00
- Category: capability-change
- Subject: GPT / ChatGPT / API
- Source: https://openai.com/index/hardening-atlas-against-prompt-injection
- Record: https://forck.live/items/322-continuously-hardening-chatgpt-atlas-against-prompt-injection

OpenAI is strengthening ChatGPT Atlas against prompt injection attacks using automated red teaming trained with reinforcement learning.

## Evidence

Verbatim from https://openai.com/index/hardening-atlas-against-prompt-injection:

> OpenAI is strengthening ChatGPT Atlas against prompt injection attacks using automated red teaming trained with reinforcement learning.

---

Record: https://forck.live/items/322-continuously-hardening-chatgpt-atlas-against-prompt-injection
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md